Published on Tue Nov 24 2015

Weakly Supervised Object Boundaries

Anna Khoreva, Rodrigo Benenson, Mohamed Omran, Matthias Hein, Bernt Schiele

State-of-the-art learning based boundary detection methods require extensive training data. Labelling object boundaries is one of the most expensive types of annotations. We propose a technique to generate weakly supervised annotations to reach high-quality boundaries.

0
0
0
Abstract

State-of-the-art learning based boundary detection methods require extensive training data. Since labelling object boundaries is one of the most expensive types of annotations, there is a need to relax the requirement to carefully annotate images to make both the training more affordable and to extend the amount of training data. In this paper we propose a technique to generate weakly supervised annotations and show that bounding box annotations alone suffice to reach high-quality object boundaries without using any object-specific boundary annotations. With the proposed weak supervision techniques we achieve the top performance on the object boundary detection task, outperforming by a large margin the current fully supervised state-of-the-art methods.